© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 11425
    Prev
    Next
    INDEX
    Explanations

    mentions of sequels in reference to films or games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ify
    -0.18
    _GB
    -0.15
    rai
    -0.14
    zelf
    -0.14
    ierz
    -0.14
    urd
    -0.14
    ÄĻki
    -0.14
    ftime
    -0.14
    sey
    -0.13
    æ¥
    -0.13
    POSITIVE LOGITS
    'gc
    0.17
    isu
    0.16
    ustr
    0.15
    itis
    0.15
     nav
    0.15
    TOTYPE
    0.14
    Advertisements
    0.14
    .TryParse
    0.14
    cest
    0.14
    GenericType
    0.14
    Activations Density 0.029%

    No Known Activations